Company will bring mission-critical face recognition and associated computer vision to low-power, low-cost devices

SAN FRANCISCO, California – Paravision, the U.S.-based leader in mission-critical computer vision, announced today that it has expanded its Edge AI offering to include full support for Ambarella’s CVflow® artificial intelligence vision processing architecture, enabling transformative solutions in enterprise access control, video security, payments, home automation, and other IoT applications.

Support of CVflow will allow Paravision to bring a wide range of its AI-based computer vision capabilities to the network edge while maintaining outstanding accuracy and processing speed. Paravision’s face recognition, which has been established as a world leader in accuracy per the National Institute of Standards and Technology’s (NIST) rigorous Face Recognition Vendor Test (FVRT), can now be deployed on ultra-compact, fanless IoT devices while maintaining greater than 30 fps face detection and image quality assessment and sub-100msec one-to-many identification.

We’re truly excited to start a new chapter in Edge AI with support of Ambarella’s CVflow architecture. Through this deep integration, we have the opportunity to enable new paradigms for user experience and industrial design, bandwidth efficiency, and biometric privacy.
Joey Pritikin, Chief Product Officer, Paravision

Ambarella has established itself as the platform of choice in computer vision-centric Edge AI due to the combination of best-of-breed image signal processing, neural network acceleration, and power efficiency in its range of CVflow system on chips (SoCs), including CV2, CV22, and CV25. By offering world-class face detection, image quality analysis, and face recognition on imaging devices powered by Ambarella SoCs, Paravision offers its partners a number of benefits:

  • Improved user experience with high-frame rate, low-latency processing in ultra-compact form factors;
  • Reduced network bandwidth load by selectively compressing or sending video, frames, or cropped images; and
  • Improved biometric privacy protection, with options to obscure or remove faces at the camera itself before ever being sent to a video stream.

The combination of Paravision software stack and Ambarella’s CVflow offers solution providers a truly compelling path to deliver face recognition and associated computer vision to a broad range of IoT applications. This is a powerful pairing for partners looking for trusted, high-performance AI-powered computer vision at the edge.
Chris Day, Vice President of Marketing and Business Development, Ambarella